Assessment of LLMs on basic bioinformatics tasks requiring multi-step reasoning and code writing
Bioinformatics · 02.10.2026 · 42 (10)
DOI: 10.1093/bioinformatics/btag749 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 30.10.2026. Verfasst von Varsha Rajesh und 3 weiteren Autor:innen. Beteiligte Einrichtung: University of Michigan, Ann Arbor, MI, USA. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCATS NIH HHS, University of Michigan Undergraduate Research Opportunities, NIH.
Abstract (Originalsprache)
Motivation Large Language Models (LLMs), AI agents and co-scientists promise to accelerate scientific discovery across fields ranging from chemistry to biology. Bioinformatics—the analysis of DNA, RNA and protein sequences plays a crucial role in biological research and is especially amenable to AI-driven automation given its computational nature. Here, we assess the bioinformatics capabilities of popular general-purpose LLMs on a set of tasks covering basic analytical questions that include code writing and multi-step reasoning in the domain. Results Utilizing questions from Rosalind, a bioinformatics educational platform, we compare the performance of the LLMs on 104 questions relative to expert ground truth and 68 760 humans with varying levels of expertise. Among the frontier LLMs evaluated (GPT-5.2, GPT-4o, GPT-3.5, Llama-3-70B, Llama-4 and Claude Sonnet 4.6), GPT-5.2 exhibited top performance, providing correct answers for 80/104 (77%) questions followed by Claude Sonnet 4.6. LLM performance varied widely depending on the biological categories of questions. While the latest generation of frontier LLM models showed overall improvements in performance, their performance in specific categories of biological questions was lower than first generation models. Overall, LLMs performance mirrored that of humans with lower performance in tasks in which humans had low performance and vice versa. However, LLMs also failed in some instances where most humans were correct and, in a few cases, LLMs excelled where most humans failed. To the best of our knowledge, this presents the first assessment of general purpose LLMs on basic bioinformatics tasks in distinct areas relative to both expert and non-expert ground truths. Availability and Implementation The complete analysis was implemented in Python; all code is available at https://github.com/SiwoResearch/lllm-bioinformatics.
Autor:innen und Institutionen
- University of Michigan, Ann Arbor, MI, USA.
- Department of Learning Health Sciences, University of Michigan Medical School, Ann Arbor, MI, USA.
- Department of Pharmacology, University of Michigan Medical School, Ann Arbor, MI, USA.
- Center for Global Health Equity, University of Michigan, Ann Arbor, MI, USA.
Förderung
- NCATS NIH HHS
- University of Michigan Undergraduate Research Opportunities
- NIH
- University of Michigan
Zitieren
APA
Rajesh, V., Blumberg, M., Jain, S., & Siwo, G. H. (2026). Assessment of LLMs on basic bioinformatics tasks requiring multi-step reasoning and code writing. Bioinformatics, 42(10). https://doi.org/10.1093/bioinformatics/btag749
Vancouver
Rajesh V, Blumberg M, Jain S, Siwo GH. Assessment of LLMs on basic bioinformatics tasks requiring multi-step reasoning and code writing. Bioinformatics. 2026;42(10). doi:10.1093/bioinformatics/btag749
BibTeX
@article{Rajesh2026,
author = {Rajesh, Varsha and Blumberg, Maceo and Jain, Shreya and Siwo, Geoffrey H},
title = {Assessment of LLMs on basic bioinformatics tasks requiring multi-step reasoning and code writing},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {10},
doi = {10.1093/bioinformatics/btag749}
}
EUVIMED